ENH: add "schema" kwarg to io.sql.get_schema method (#38146)

* Added schema kwarg and test

* Added type hinting and marked GH issue in test case

* fixed pep8 issues

* Fixed sorting on import

* move comment

* styling

* review comment

* docstring

Co-authored-by: Gregory Livschitz <[email protected]>

Author: arw2019

doc/source/whatsnew/v1.2.0.rst

@@ -260,6 +260,7 @@ Other enhancements
 - Added :meth:`~DataFrame.set_flags` for setting table-wide flags on a Series or DataFrame (:issue:`28394`)
 - :meth:`DataFrame.applymap` now supports ``na_action`` (:issue:`23803`)
 - :class:`Index` with object dtype supports division and multiplication (:issue:`34160`)
+- :meth:`io.sql.get_schema` now supports a ``schema`` keyword argument that will add a schema into the create table statement (:issue:`28486`)
 - :meth:`DataFrame.explode` and :meth:`Series.explode` now support exploding of sets (:issue:`35614`)
 - :meth:`DataFrame.hist` now supports time series (datetime) data (:issue:`32590`)
 - :meth:`.Styler.set_table_styles` now allows the direct styling of rows and columns and can be chained (:issue:`35607`)

pandas/io/sql.py

@@ -7,7 +7,7 @@
 from datetime import date, datetime, time
 from functools import partial
 import re
-from typing import Iterator, Optional, Union, overload
+from typing import Iterator, List, Optional, Union, overload
 import warnings
 
 import numpy as np
@@ -1455,9 +1455,22 @@ def drop_table(self, table_name, schema=None):
             self.get_table(table_name, schema).drop()
             self.meta.clear()
 
-    def _create_sql_schema(self, frame, table_name, keys=None, dtype=None):
+    def _create_sql_schema(
+        self,
+        frame: DataFrame,
+        table_name: str,
+        keys: Optional[List[str]] = None,
+        dtype: Optional[dict] = None,
+        schema: Optional[str] = None,
+    ):
         table = SQLTable(
-            table_name, self, frame=frame, index=False, keys=keys, dtype=dtype
+            table_name,
+            self,
+            frame=frame,
+            index=False,
+            keys=keys,
+            dtype=dtype,
+            schema=schema,
         )
         return str(table.sql_schema())
 
@@ -1588,9 +1601,13 @@ def _create_table_setup(self):
             create_tbl_stmts.append(
                 f"CONSTRAINT {self.name}_pk PRIMARY KEY ({cnames_br})"
             )
-
+        if self.schema:
+            schema_name = self.schema + "."
+        else:
+            schema_name = ""
         create_stmts = [
             "CREATE TABLE "
+            + schema_name
             + escape(self.name)
             + " (\n"
             + ",\n  ".join(create_tbl_stmts)
@@ -1845,14 +1862,20 @@ def drop_table(self, name, schema=None):
         drop_sql = f"DROP TABLE {_get_valid_sqlite_name(name)}"
         self.execute(drop_sql)
 
-    def _create_sql_schema(self, frame, table_name, keys=None, dtype=None):
+    def _create_sql_schema(self, frame, table_name, keys=None, dtype=None, schema=None):
         table = SQLiteTable(
-            table_name, self, frame=frame, index=False, keys=keys, dtype=dtype
+            table_name,
+            self,
+            frame=frame,
+            index=False,
+            keys=keys,
+            dtype=dtype,
+            schema=schema,
         )
         return str(table.sql_schema())
 
 
-def get_schema(frame, name, keys=None, con=None, dtype=None):
+def get_schema(frame, name, keys=None, con=None, dtype=None, schema=None):
     """
     Get the SQL db table schema for the given frame.
 
@@ -1870,7 +1893,12 @@ def get_schema(frame, name, keys=None, con=None, dtype=None):
     dtype : dict of column name to SQL type, default None
         Optional specifying the datatype for columns. The SQL type should
         be a SQLAlchemy type, or a string for sqlite3 fallback connection.
+    schema: str, default: None
+        Optional specifying the schema to be used in creating the table.
 
+        .. versionadded:: 1.2.0
     """
     pandas_sql = pandasSQL_builder(con=con)
-    return pandas_sql._create_sql_schema(frame, name, keys=keys, dtype=dtype)
+    return pandas_sql._create_sql_schema(
+        frame, name, keys=keys, dtype=dtype, schema=schema
+    )

pandas/tests/io/test_sql.py

@@ -865,6 +865,13 @@ def test_get_schema(self):
         create_sql = sql.get_schema(self.test_frame1, "test", con=self.conn)
         assert "CREATE" in create_sql
 
+    def test_get_schema_with_schema(self):
+        # GH28486
+        create_sql = sql.get_schema(
+            self.test_frame1, "test", con=self.conn, schema="pypi"
+        )
+        assert "CREATE TABLE pypi." in create_sql
+
     def test_get_schema_dtypes(self):
         float_frame = DataFrame({"a": [1.1, 1.2], "b": [2.1, 2.2]})
         dtype = sqlalchemy.Integer if self.mode == "sqlalchemy" else "INTEGER"